Local Sub-models Research Articles

Ensemble Learning-Based Correlation Coefficient Method for Robust Diagnosis of Voltage Sensor and Short-Circuit Faults in Series Battery Packs

Accurate and reliable multi-fault diagnosis of battery packs is crucial to the safe operation of electric vehicles. To this end, this paper proposes a systematically improved Correlation Coefficient (CC) method by utilizing multivariate statistical analysis and Bayesian probability theory under the framework of ensemble learning. Specifically, different window-widths are first selected in an appropriate value range, and the CC signals between cross-cell voltages for each fixed window-width are calculated to create different local sub-models. Then, in each sub-model, an independent component analysis-based fault diagnosis is implemented to obtain the local diagnostic result, and the results of all sub-models are integrated as an Ensemble Fault Probability (EFP) and an Ensemble Contribution Rate (ECR) through Bayesian probabilistic ensemble interface. Once the EFP exceeds its threshold, a fault is considered to be detected and the ECR is subsequently applied along with the cross-cell sensor topology to identify the fault type (short-circuit or sensor fault) and locate the accurate position of the failed battery cell/sensor. In-depth theoretical analysis and sufficient comparative experiments on a real Lithium-ion battery packs test platform demonstrate that the proposed approach becomes more robust and reliable than the conventional CC-based methods, and also has better physical interpretability.

T-S fuzzy sliding mode control for double-fed induction generator-based wind energy system with a membership function-dependent [formula omitted]-approach

This study is mainly concerned with fuzzy integral sliding mode control (FISMC) design for double-fed induction generator (DFIG)-based wind energy system (WES) under membership function-dependent H∞ approach. To do this, a nonlinear DFIG based WES is considered with exogenous load torque variation. Then, by utilizing Takagi–Sugeno fuzzy approach, the proposed nonlinear system can be expressed as a sum of local sub-models with the help of IF-THEN rules. A suitable FISMC is designed with a reaching law condition for the proposed DFIG-based WES with the disturbances. A new fuzzy-based Lyapunov function is constructed, and the H∞ performance index is calculated for external disturbances under membership function-dependent H∞ approach. The obtained performance index of membership function-dependent H∞ approach can be improved 10% than the conventional H∞ approach. Finally, the simulation results are given the better stable performance of the DFIG-based WES under the designed FISMC, and the comparison results verify the efficacy of the proposed method.

The numerical modeling of heterogeneities by the finite element method in 3D setting

The paper proposes a variant of the algorithm for 3D numerical simulation of the rock mass stress-strain state in the vicinity of structural heterogeneities by the finite element method. Modeling of the stress-strain state is used, among other things, when analyzing the fractures in the rock mass, which can occur as a breakage or a shear along the weakening planes. The rock massif has a block structure, where the boundaries of various-scale blocks are structural disturbances of different orders. The surface planes of structural heterogeneities usually have complex geometry and spatial orientation, so the most adequate results can be obtained by 3D modeling of the disturbed rock mass. Besides, it is important to take into account the type of the stress-strain state, which can be not only gravitational, but also gravitational-tectonic, including horizontal loading of the rock mass. Accounting these features allows obtaining the most adequate geomechanical model of the studied object. For this purpose, the authors have studied and analyzed the existing approaches to modeling heterogeneities in the rock mass, including using the Goodman contact element, and developed its 3D modification. A mining engineer needs to have a handy tool that allows creating and editing a geomechanical model, taking into account mining plans and related sections. The model navigation, edition of its individual blocks to specify geology and creation of local sub-models make it necessary to use structured meshes of finite elements. Modification of the model with the introduction of contact elements entails the creation of an unstructured mesh, which complicates further manipulations with it. To solve this problem, a special zero element was developed, which allows saving a structured mesh format when implementing a contact element. This zero element, like the contact element, has zero thickness, and its nodes have averaged strength characteristics of adjacent blocks of the undisturbed rock mass. The result of these studies is a tool that allows creating 3D models of the rock mass stress-strain state, taking into account its structural heterogeneities and preserving the regular structure of the finite element mesh.

Experimental and numerical validation of a proportional solenoid valve based on the data-driven model

Solenoid valves are widely used in mechatronics, robotic systems and industrial occasions. An accurate model is very important for the design and control of a solenoid valve. The dynamical model of the solenoid valve is difficult to obtain due to the complexity of the structure and the interaction of multiple physical fields. This paper proposes two kinds of model of solenoid valve: grey box model and black box model, on the basis of experimental data. ARX model is selected as the basic structure of the grey box model. After clustering the data with the fuzzy c-means algorithm, the overall experimental data is divided into several local linear sub-models, and the model coefficients of the local linear model are obtained by partial least square regression. The overall expression of the model is obtained by combining the local sub-models with membership degree. For the black box model, support vector regression algorithm is used to identify. On the basis of selecting the appropriate parameters, we obtain the black box model of solenoid valve based on data. For the above two models, we carry out experimental verification and error analysis, and compare with the traditional modelling method. According to the results, it can be seen that on the basis of the experimental data, using the data-driven method to construct the model has many advantages, avoiding complex physical analysis, and has high accuracy. The model with high precision will be used in the accurate control and observing estimation of the solenoid valve.

Goal oriented error estimation in multi-scale shell element finite element problems

A major challenge with modern aircraft design is the occurrence of structural features of varied length scales. Structural stiffness can be accurately represented using homogenisation, however aspects such as the onset of failure may require information on more refined length scale for both metallic and composite components. This work considers the errors encountered in the coarse global models due to the mesh size and how these are propagated into detailed local sub-models. The error is calculated by a goal oriented error estimator, formulated by solving dual problems and Zienkiewicz-Zhu smooth field recovery. Specifically, the novel concept of this work is applying the goal oriented error estimator to shell elements and propagating this error field into the continuum sub-model. This methodology is tested on a simplified aluminium beam section with four different local feature designs, thereby illustrating the sensitivity to various local features with a common global setting. The simulations show that when the feature models only contained holes on the flange section, there was little sensitivity of the von Mises stress to the design modifications. However, when holes were added to the webbing section, there were large stress concentrations that predicted yielding. Despite this increase in nominal stress, the maximum error does not significantly change. However, the error field does change near the holes. A Monte Carlo simulation utilising marginal distributions is performed to show the robustness of the multi-scale analysis to uncertainty in the global error estimation as would be expected in experimental measurements. This shows a trade-off between Saint-Venant’s principle of the applied loading and stress concentrations on the feature model when investigating the response variance.

A self-organizing multi-model ensemble for identification of nonlinear time-varying dynamics of aerial vehicles

This article presents a novel identification approach which can deal with nonlinear and time-varying characteristics of complex dynamic systems, especially an aerial vehicle in the entire flight envelope. A set of local sub-models are first developed at different operating points of the system, and subsequently a self-organizing multi-model ensemble is introduced to aggregate the outputs of the local models as a single model. The number of employed local models in the proposed multi-model ensemble is optimized using a novel self-organizing approach. Also, wavelet neural networks, which combine both the universal approximation property of neural networks and the wavelet decomposition capability, are used as the local models of the proposed method. In addition, a generalized online sequential extreme learning machine is adopted in the introduced approach to determine the optimal validity function of the local models at each time step. Finally, the introduced self-organizing multi-model ensemble is applied to the NASA Generic Transport Model as a complex nonlinear system to demonstrate the effectiveness of the proposed identification approach. Furthermore, the results obtained from the conventional artificial neural networks are carefully compared with those from the wavelet neural networks, which are employed as the local models of the introduced multi-model ensemble. The simulation results suggest that the introduced wavelet neural network–based self-organizing multi-model ensemble can be used satisfactorily as the prediction model of model-based control systems for long prediction horizons.

Identification of nonlinear time‐varying systems using wavelet neural networks

AbstractThe dynamic model of an aircraft changes significantly by altering the flight speed and the vehicle altitude. Thus, a conventional aircraft has a nonlinear time‐varying dynamic model in different regions of the flight envelope, and a dynamic model developed for a specific operating point is not valid in the entire flight envelope. This paper presents a novel identification approach that can deal with nonlinear and time‐varying characteristics of complex dynamic systems, especially an aerial vehicle in the entire flight envelope. In this regard, a set of local submodels are first developed at different operating points of the system, and subsequently, a multimodel structure is introduced to aggregate the outputs of the local models as a single model. Wavelet Neural Networks (WNNs), which combine both the universal approximation property of neural networks and the wavelet decomposition capability, are used as the local models of the proposed scheme. Also, three different approaches for determining the validity functions of the local models are introduced to allow for identifying the time‐varying dynamics of the system. The simulation results obtained for the Generic Transport Model aircraft suggest that the proposed WNN‐based multimodel structure can be used satisfactorily as the prediction model of model‐based flight control systems for long prediction horizons.

Robust $$ H_{\infty } $$ Fault-Tolerant Control for Discrete-Time Nonlinear System with Actuator Faults and Time-Varying Delays Using Nonlinear T–S Fuzzy Models

In this paper, the problem of fault estimation and fault-tolerant control for a class of nonlinear discrete-time system state time-varying delay and actuator fault is investigated. This class of systems is represented through the Takagi–Sugeno (T–S) fuzzy model with nonlinear functions satisfying some sector-bounded conditions. By adding these nonlinear functions in the local sub-models, the observer and controller can be designed with fewer rules and less computation burden. The method proceeds in two steps: first, a full-order fuzzy fault estimation observer (FFEO) design is proposed to estimate the actuator faults and the nonlinear functions in the T–S models. Second, based on the online fault estimation, a dynamic output feedback fault-tolerant controller (DOFTC) is then designed to compensate the effect of faults by stabilizing the closed-loop system. Furthermore, sufficient less conservative delay-dependent conditions for the existence of the desired FFEO and DOFTC are given in terms of linear matrix inequalities by employing the fuzzy Lyapunov–Krasovskii function and free-weighting approach. Finally, a practical example is given to show the effectiveness and advantages of the proposed approach.

Geographical random forests: a spatial extension of the random forest algorithm to address spatial heterogeneity in remote sensing and population modelling

Machine learning algorithms such as Random Forest (RF) are being increasingly applied on traditionally geographical topics such as population estimation. Even though RF is a well performing and generalizable algorithm, the vast majority of its implementations is still ‘aspatial’ and may not address spatial heterogenous processes. At the same time, remote sensing (RS) data which are commonly used to model population can be highly spatially heterogeneous. From this scope, we present a novel geographical implementation of RF, named Geographical Random Forest (GRF) as both a predictive and exploratory tool to model population as a function of RS covariates. GRF is a disaggregation of RF into geographical space in the form of local sub-models. From the first empirical results, we conclude that GRF can be more predictive when an appropriate spatial scale is selected to model the data, with reduced residual autocorrelation and lower Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) values. Finally, and of equal importance, GRF can be used as an effective exploratory tool to visualize the relationship between dependent and independent variables, highlighting interesting local variations and allowing for a better understanding of the processes that may be causing the observed spatial heterogeneity.

Object tracking with collaborative extreme learning machines

We propose a novel collaborative discriminative model based on extreme learning machine (ELM) for object tracking in this paper. In order to represent the object more precisely, we first propose a new collaborative discriminative representation model, which includes both a global discriminative sub-model and a local discriminative sub-model. Different from traditional local representation models, in particular, our local sub-model integrates several classifiers which have structural relations to improve the expression. The global discriminative model represents the appearance comprehensively while the local discriminative sub-model can effectively address occlusions and assist the update. Second, to have better combination of these sub-models, we propose a novel collaboration strategy based on the Kullback-Leibler (KL) distance. The novel strategy can determine the weights of the sub-models adaptively by measuring their KL distances reciprocally. Third, we introduce ELM into tracking and adopt it to build both the global and the local discriminative sub-models simultaneously. Since ELM has a good generalization performance and is robust to the imbalance of the training samples, it is suitable to be used for tracking. Experimental results demonstrate that our method can achieve comparable performance to many state-of-the-art tracking approaches.

Bi-level cellular agent-based model: Simulation of potential impacts of high-speed rail on land cover change in the Lisbon Metropolitan Area, Portugal

This paper presents a bi-level cellular agent-based model (ABM) framework, which incorporates a land cover change sub-model at the local level and a socioeconomic activity growth sub-model at the regional level. In the local sub-model, a land cell is set as an agent, of which the land-cover change decisions are mainly influenced by spatial mixed logit models. The regional sub-model is driven by fixed effects panel models, generating estimates of socioeconomic variables, thanks to the accessibility improvement and local land development. The re - gional outputs are also distributed into the local sub-models as their in - puts. By inputting the historical data of the Lisbon Metropolitan Area (LMA) in 1991, a back-casting simulation was executed for validation. It compares the simulated outputs in 2011 with the actual reference data, based on multiple resolution goodness-of-fit (MRG) methods. Three scenarios are then designed to study the potential impacts of high-speed rail (HSR) on land-cover change in the LMA according to different proposals of HSR station locations. The scenarios indicate that without HSR the un-built lands in the LMA are likely to be largely developed if the annual GDP growth rate holds at 1.5 percent. With HSR the simulation suggests that land development is accelerated. The opening of an additional HSR station in Setubal besides Lisbon-Orien - te does not act as an obstacle to the urbanization process in the LMA, although it reduces HSR speed and the resulting regional accessibility. However, the contribution of the added station to the land-develop - ment process is also limited. Only a few areas are likely to benefit.

Sustainability analysis of complex dynamic systems using embodied energy flows: The eco-bond graphs modeling and simulation framework

This article presents a general methodology for modeling complex dynamic systems focusing on sustainability properties that emerge from tracking energy flows.We adopt the embodied energy (emergy) concept that traces all energy transformations required for running a process. Thus, energy at any process within a system is studied in terms of all the energy previously invested to support it (up to the primary sources) and therefore sustainability can be analyzed structurally.These ideas were implemented in the bond graph framework, a modeling paradigm where physical variables are explicitly checked for adherence to energy conservation principles.The results are a novel Ecological Bond Graphs (EcoBG) modeling paradigm and the new EcoBondLib library, a set of practical ready-to-use graphical models based on EcoBG principles and developed under the Modelica model encoding standard.EcoBG represents general systems in a three-faceted fashion, describing dynamics at their mass, energy, and emergy facets. EcoBG offers a scalable graphical formalism for the description of emergy dynamic equations, resolving some mathematical difficulties inherited from the original formulation of the equations.The core elements of EcoBG offer a soundly organized mathematical skeleton upon which new custom variables and indexes can be built to extend the modeling power. This can be done safely, without compromising the correctness of the core energy balance calculations. As an example we show how to implement a custom sustainability index at local submodels, for detecting unsustainable phases that are not automatically discovered when using the emergy technique alone.The fact that we implemented EcoBondLib relying on the Modelica technology opens up powerful possibilities for studying sustainability of systems with interactions between natural and industrial processes. Modelica counts on a vast and reusable knowledge base of industrial-strength models and tools in engineering applications, developed by the Modelica community throughout decades.

Distributed Prognostics Based on Structural Model Decomposition

Within systems health management, prognostics focuses on predicting the remaining useful life of a system. In the model-based prognostics paradigm, physics-based models are constructed that describe the operation of a system, and how it fails. Such approaches consist of an estimation phase, in which the health state of the system is first identified, and a prediction phase, in which the health state is projected forward in time to determine the end of life. Centralized solutions to these problems are often computationally expensive, do not scale well as the size of the system grows, and introduce a single point of failure. In this paper, we propose a novel distributed model-based prognostics scheme that formally describes how to decompose both the estimation and prediction problems into computationally-independent local subproblems whose solutions may be easily composed into a global solution. The decomposition of the prognostics problem is achieved through structural decomposition of the underlying models. The decomposition algorithm creates from the global system model a set of local submodels suitable for prognostics. Computationally independent local estimation and prediction problems are formed based on these local submodels, resulting in a scalable distributed prognostics approach that allows the local subproblems to be solved in parallel, thus offering increases in computational efficiency. Using a centrifugal pump as a case study, we perform a number of simulation-based experiments to demonstrate the distributed approach, compare the performance with a centralized approach, and establish its scalability.

A Passenger Traffic Assignment Model with Capacity Constraints for Transit Networks

A model is provided to capture capacity phenomena in passenger traffic assignment to a transit network. These pertain to the interaction of passenger traffic and vehicle traffic: vehicle seat capacity drives the internal comfort, vehicle total capacity determines internal comfort and also platform waiting, passenger flows at vehicle egress and access interplay with dwell time, dwell time drives track occupancy and in turn the period frequency of any service that passes the station along the line of operations, and then service frequency influences service capacity and platform waiting. These phenomena are dealt with by line of operations on the basis of a set of local models yielding specific flows or costs. The topological order of the line is used to devise two line models of, respectively, flow loading and cost setting, each of which calls its local sub-models. The pair of line algorithms amounts to a complex cost-flow relationship at the level of the line. The line model is used as a sub-model in passenger assignment to network hyperpaths, where line pairs of access-egress stations constitute leg links. The properties of static traffic equilibrium for both vehicles and passengers are established.

A Distributed Approach to System-Level Prognostics

Prognostics, which deals with predicting remaining useful life of components, subsystems, and systems, is a key technology for systems health management that leads to improved safety and reliability with reduced costs. The prognostics problem is often approached from a component-centric view. However, in most cases, it is not specifically component life- times that are important, but, rather, the lifetimes of the systems in which these components reside. The system-level prognostics problem can be quite difficult due to the increased scale and scope of the prognostics problem and the relative lack of scalability and efficiency of typical prognostics approaches. In order to address these issues, we develop a distributed solution to the system-level prognostics problem, based on the concept of structural model decomposition. The system model is decomposed into independent submodels. Independent local prognostics subproblems are then formed based on these local submodels, resulting in a scalable, efficient, and flexible distributed approach to the system-level prognostics problem. We provide a formulation of the system-level prognostics problem and demonstrate the approach on a four-wheeled rover simulation testbed. The results show that the system-level prognostics problem can be accurately and efficiently solved in a distributed fashion.

Global and local modelling in RBF networks

Radial basis function networks are traditionally known as local approximation networks as they are composed by a number of elements which, individually, mainly take care of the approximation about a specific area of the input space. Then, the joint global output of the network is obtained as a linear combination of the individual elements' output. However, in the network optimization, the performance of the global model is normally the only objective to optimize. This might cause a deficient local modelling of the input space, thus partially losing the local character of this type of models. This work presents a modified radial basis function network that maintains the approximation capabilities of the local sub-models whereas the model is globally optimized. This property is obtained thanks to a special partitioning of the input space, that leads to a direct global–local optimization. A learning methodology adapted to the proposed model is used in the simulations, consisting of a clustering algorithm for the initialization of the centers and a local search technique. In the experiments, the proposed model shows satisfactory local and global modelling capabilities both in artificial and real applications.

The TaSe-NF model for function approximation problems: Approaching local and global modelling

Optimization of the local sub-models when using neuro-fuzzy systems to model input/output data can be spoiled during the global optimization process, therefore special care has to be taken to avoid this loss. Some approaches involving grid input space partitioning that optimize local sub-models whilst still obtaining a good global system performance have appeared. However, this is a more complex task for radial basis function networks, scatter-partitioning fuzzy systems and neuro-fuzzy models in general. This work presents a modified neuro-fuzzy model, known as the TaSe-NF model, which is a special case of a scatter-partitioned Takagi–Sugeno–Kang fuzzy system or normalized radial basis function neural network. The TaSe-NF model maintains the optimization properties of the local sub-models (fuzzy rules or RBF nodes) when the model is globally optimized thanks to the modified calculation of the final normalized activation of the rules, which provides an appropriate input space partitioning to achieve these objectives. To show the characteristics of the proposed model, a learning methodology for this model, which consists of a clustering algorithm especially suited to function approximation problems, a local search technique and a membership function merging approach, with the objective of improving the transparency, i.e. ease of interpretability, of the extracted fuzzy rule set is also proposed.

Output Feedback Fuzzy Controller Design With Local Nonlinear Feedback Laws for Discrete-Time Nonlinear Systems

This paper considers the output feedback control problem for nonlinear discrete-time systems, which are represented by a type of fuzzy systems with local nonlinear models. By using the estimations of the states and nonlinear functions in local models, sufficient conditions for designing observer-based controllers are given for discrete-time nonlinear systems. First, a separation property, i.e., the controller and the observer can be independently designed, is proved for the class of fuzzy systems. Second, a two-step procedure with cone complementarity linearization algorithms is also developed for solving the H( ∞) dynamic output feedback (DOF) control problem. Moreover, for the case where the nonlinear functions in local submodels are measurable, a convex condition for designing H(∞) controllers is given by a new DOF control scheme. In contrast to the existing methods, the new methods can design output feedback controllers with fewer fuzzy rules as well as less computational burden, which is helpful for controller designs and implementations. Lastly, numerical examples are given to illustrate the effectiveness of the proposed methods.

Using Bayesian Graphical Models to Model Biases in Observational Studies and to Combine Multiple Sources of Data: Application to Low Birth Weight and Water Disinfection by-Products

SummaryData in the social, behavioural and health sciences frequently come from observational studies instead of controlled experiments. In addition to random errors, observational data typically contain additional sources of uncertainty such as missing values, unmeasured confounders and selection biases. Also, the research question is often different from that which a particular source of data was designed to answer, and so not all relevant variables are measured. As a result, multiple sources of data are often necessary to identify the biases and to inform about different aspects of the research question. Bayesian graphical models provide a coherent way to connect a series of local submodels, based on different data sets, into a global unified analysis. We present a unified modelling framework that will account for multiple biases simultaneously and give more accurate parameter estimates than standard approaches. We illustrate our approach by analysing data from a study of water disinfection by-products and adverse birth outcomes in the UK.

Agrupaciones de modelos locales con descripción externa. Aplicación a una planta de frío solar

In this paper a method for creating linear local submodels is presented ana analyzed. The main contribution is the use of a weighting function based on input-output signals alone. This choice has the advantage of simplifying some aspects related to the model building task. The representational capacity remains the same, being compared in the paper with other techniques. The simplification mentioned above is an important one since it allows the method to the industrial practice of process identification. The resulting identification technique is illustrated using a simulated process (proposed by Narendra) and a real process consisting of a cooling solar plant. These examples prove the applicability of the method as a simple tool usable in industry.